AI Paper Atlas

Research map / Image generation / Super-resolution

ATGV-Net: Accurate Depth Super-Resolution

Gernot Riegler, Matthias Rüther, Horst Bischof

ECCV 2016 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 158 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the variational ATGV model on top of the CNN without joint training (ablation)ATGV-Net · Middlebury noisy x4, ArtRMSE: 3.55 -> 3.40Improved
add the variational ATGV model on top of the CNN without joint training (ablation)ATGV-Net · Middlebury noisy x4, BooksRMSE: 2.41 -> 2.24Improved
train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation)ATGV-Net · Middlebury noisy x4, ArtRMSE: 3.40 -> 2.98Improved
train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation)ATGV-Net · Middlebury noisy x4, BooksRMSE: 2.24 -> 1.72Improved
train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation)ATGV-Net · Middlebury noisy x4, MoebiusRMSE: 2.51 -> 1.95Improved
add the variational ATGV model on top of the CNN without joint training (ablation)ATGV-Net · Middlebury clean x2, ConesRMSE: 1.0275 -> 1.0145Improved
train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation)ATGV-Net · Middlebury clean x4, VenusRMSE: 0.4124 -> 0.3764Improved
train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation)ATGV-Net · Middlebury clean x2, TsukubaRMSE: 2.3197 -> 2.3846Hurt
train the CNN and variational model end-to-end by unrolling the primal-dual iterations (ablation)ATGV-Net · Middlebury clean x4, TsukubaRMSE: 6.4223 -> 6.6327Hurt
add the variational ATGV model on top of the CNN without joint training (ablation)ATGV-Net · Middlebury clean x2, TeddyRMSE: 0.8201 -> 0.8374Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy